LogoLogo
  • Welcome to Gretel!
  • Gretel Basics
    • Getting Started
      • Quickstart
      • Blueprints
      • Use Case Examples
      • Environment Setup
        • Console
        • SDK
      • Projects
      • Inputs and Outputs
      • Gretel Connectors
        • Object Storage
          • Amazon S3
          • Google Cloud Storage
          • Azure Blob
        • Database
          • MySQL
          • PostgreSQL
          • MS SQL Server
          • Oracle Database
        • Data Warehouse
          • Snowflake
          • BigQuery
          • Databricks
        • Gretel Project
    • Release Notes
      • Platform Release Notes
        • May 2025
        • April 2025
        • March 2025
        • February 2025
        • January 2025
        • December 2024
        • November 2024
        • October 2024
        • September 2024
        • August 2024
        • July 2024
        • June 2024
      • Console Release Notes
        • January 2025
        • December 2024
        • November 2024
        • October 2024
        • September 2024
        • August 2024
      • Python SDKs
  • Create Synthetic Data
    • Gretel Safe Synthetics
      • Transform
        • Reference
        • Examples
        • Supported Entities
      • Synthetics
        • Gretel Tabular Fine-Tuning
        • Gretel Text Fine-Tuning
        • Gretel Tabular GAN
        • Benchmark Report
        • Privacy Protection
      • Evaluate
        • Synthetic Quality & Privacy Report
        • Tips to Improve Synthetic Data Quality
        • Data Privacy 101
      • SDK
    • Gretel Data Designer
      • Getting Started with Data Designer
      • Define your Data Columns
        • Column Types
        • Add Constraints to Columns
        • Custom Model Configurations
        • Upload Files as Seeds
      • Building your Dataset
        • Seeding your Dataset
        • Generating Data
      • Generate Realistic Personal Details
      • Structured Outputs
      • Code Validation
      • Data Evaluation
      • Magic Assistance
      • Using Jinja Templates
  • Gretel Playground [Legacy]
    • Getting Started
    • Prompts Tips & Best Practices
    • FAQ
    • SDK Examples
    • Tutorials
    • Videos
    • Gretel Playground [Legacy] Inference API
    • Batch Job SDK
  • Reference
    • Gretel's Python Client
    • Gretel’s Open Source Synthetic Engine
    • Gretel’s REST API
    • Homepage
    • Model Suites
Powered by GitBook
On this page
  • Using Playground in Console
  • Use Playground via the Gretel SDK
  • Example 1: I want some data, but I don’t have concrete structure for that data
  • Example 2: I want data and I know the structure I need
  • Example 3: I have data and want to add new columns to it
  • Example 4: I have data and want to modify it

Was this helpful?

Export as PDF
  1. Gretel Playground [Legacy]

Getting Started

PreviousGretel Playground [Legacy]NextPrompts Tips & Best Practices

Last updated 1 month ago

Was this helpful?

Using Playground in Console

An easy way to try out Playground is to start in the Gretel Console.

  1. and select "Playground".

  2. Try out an example prompt, or use your own. Then click "Generate".

  3. Pro tip: review the page to get the best results from your input

  4. Click the 3 dots to download your dataset, or click "Batch Data" to generate more than 100 records

Use Playground via the Gretel SDK

You can use Playground operationally through the Gretel SDK.

If you're feeling stuck, you may find the following use cases helpful to get started.

Example 1: I want some data, but I don’t have concrete structure for that data

Let’s say we want to generate data that represents consumer packaged goods inventory.

We can workshop prompt ideas first using the "Natural language" option of Playground. You can find this tab in the playground.

Try asking:

What are common headers of a consumer packaged goods (CPG) inventory dataset?

or

Help me write a prompt for a large language model (LLM) to create a dataset that represents consumer packaged goods (CPG) inventory

We can use the responses to start with a prompt and then narrow it down to be more specific for the data we're looking for.

Example 2: I want data and I know the structure I need

Example 3: I have data and want to add new columns to it

This feature is available in the playground as well as the SDK. In playground, select the option to add columns to an existing dataset.

Upload your dataset (csv or jsonl format), then use the prompt template to describe the new columns you want to add.

To do this via the SDK, make sure to write a clear prompt describing the new column you want to add to your data.

Example 4: I have data and want to modify it

  1. Select "Add columns to existing datasets"

  2. Upload your CSV or JSON(L) file into the box

  3. Ensure the uploaded file looks correct in the output section

  4. Edit the prompt as appropriate to add the columns you'd like, with detailed description of rules for generating each column as appropriate

  5. Click generate

Create a if you don't already have one in order to get your API key.

Start from an or create your own

Pro tip: After submitting a prompt to Playground, you can further refine the results by adding sample data from the output. Select "Add an example to improve result" and choose "Import current output". You can make edits to the output to match what you're looking for.

For best results, describe the data you're looking to create in a clear manner: like using bullet points and clear descriptions for each column. Review the doc for best practices.

You can see an example of adding columns in the .

⭐
Gretel account
example notebook
Prompts
Playground inference API 101 Blueprint
Sign into the console
Prompts
Download CSV button and Batch Button
Select tabular data for generating data, or use natural language mode for Q&A
add columns to dataset